Back to skill

Security audit

AI塔罗指引

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese tarot-reading and learning guide with no local execution, persistence, or credential access, though generated HTML reports may load Chart.js from a CDN if used.

Before installing, note that the skill is written for Chinese-language tarot use and may generate an HTML report that loads Chart.js from a CDN. Avoid putting sensitive personal details into reports that execute third-party JavaScript, or ask the agent to generate charts with local CSS/SVG/canvas instead.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:139
Finding

Unpinned External JavaScript Dependency in Generated HTML Reports

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad conversational phrases such as '帮我算' and '帮我占卜', which can match ordinary user messages outside a clearly scoped tarot request. Over-broad activation can cause unintended skill invocation, leading the agent to load this skill in irrelevant contexts and potentially override safer or more appropriate behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation rules allow broad intent-based matching for loosely defined requests like learning, history, or 'help me interpret,' without clear boundaries or disambiguation logic. In an agent environment, this increases the chance of accidental routing, context hijacking, or inappropriate generation of occult guidance when the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file is entirely written in Chinese and presents the skill/reference content in a single fixed language. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is entirely written in Chinese, with no indication that users may choose another language or that the Chinese-only presentation is required for a justified regional purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file is entirely written in Chinese and presents the skill content only in that language, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all user-facing guidance in a single language and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

L141 明确要求生成“单文件,零外部依赖”的 HTML 报告,但 L142 又要求“使用Chart.js CDN绘制元素分布图(如有需要)”。通过 CDN 加载脚本本质上依赖外部网络资源,因此这两条实现说明彼此冲突,属于文档意图与实际实现要求不一致。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown reference forces a specific language throughout the file and does not mention that the user can choose another language or that the Chinese-only format is intentionally region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that other language options are available. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The markdown states that unless the user explicitly specifies otherwise, the skill will default to the Rider-Waite-Smith system. This imposes a particular framework by default rather than offering a neutral choice, which is a natural-language policy concern when the skill could reasonably ask the user to choose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all user-facing instructional content in a single language, Chinese, and does not indicate that the skill is region-specific or that users can opt into another language. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale policy issue.

Content

No source excerpt is available for this finding.